Improving the Performance of the Sparse Representation Based Classification in BCI Systems, by Enhancing the Process of Feature Extraction and Using an Optimized Sparse Solution Finding Algorithm

Mirjalili, Alireza; Abootalebi, Vahid; Sadeghi, Mohammad Taghi

doi:10.22041/ijbme.2014.14701

Improving the Performance of the Sparse Representation Based Classification in BCI Systems, by Enhancing the Process of Feature Extraction and Using an Optimized Sparse Solution Finding Algorithm

Document Type : Full Research Paper

Authors

Alireza Mirjalili ¹

Vahid Abootalebi ²

Mohammad Taghi Sadeghi ²

¹ M.Sc Student, Faculty of Electrical and Computer Engineering, Yazd University, Yazd, Iran

² Assistant Professor, Faculty of Electrical and Computer Engineering, Yazd University, Yazd, Iran

https://doi.org/10.22041/ijbme.2014.14701

Abstract

In recent years, Brain-Computer Interface (BCI) has been noted as a new means of communication between the human brain and his surroundings. In order to set up such a system, the collaboration of several blocks, such as data recording, signal processing and user interface are needed. The signal processing block, includes two units of preprocessing and pattern recognition. Pattern recognition block itself involves two phases: feature extraction and classification. In this paper, the sparse representation based classification (SRC) has been used in the classification block. There are two important issues in using the SRC. These are creating an appropriate dictionary matrix and adopting a proper method for finding the sparse solution for an input data. In this research study, the dictionary matrix is formed by extracting an optimal set of features from the training data. Toward this goal, the common spatial patterns algorithm (CSP) is first used. Sensitivity to noise and the over learning phenomena are the main drawbacks of the CSP algorithm. In order to remove these problems, the regularized common spatial patterns algorithm (RCSP) is employed. In previous studies in within the BCI framework, the standard BP algorithm has been used to find a sparse solution. The main disadvantage of the BP algorithm is that the method is computationally expensive. To overcome this weakness, a recently proposed algorithm namely the SL0 approach is used instead. Our experimental results show that when the number of training samples is limited, the RCSP algorithm outperforms the CSP one. Using the features derived from the RCSP, the average detection rate is in average increased by a factor of 7.53%. Our classification results also show that using the SL0 algorithm, the classification process is highly speeded up as compared to the BP algorithm while an almost equivalent accuracy is achieved.

Keywords

Brain Computer Interface

Motor Imagery

regularized common spatial patterns

sparse representation based-classification

smoothed L0-norm

Subjects

[1] Z. Cashero, "Comparison of EEG preprocessing methods to Improved the classification of p300 trials" M. Sc Thesis, Department of Computer Science Colorado State University, 2011.

[2] J. N. Mak, J. R. Wolpaw, “Clinical Applications of Brain Computer Interfaces: Current State and Future Prospects” IEEE reviews in biomedical engineering 2, 187-199, 2009.

[3] J. Wright, A. Yang, S. Sastry and Y. Ma, "Robust face recognition via sparse representation” IEEE Trans Pattern Anal Mach Intell 31 (2), 210-227, 2009.

[4] Y. Shin, S. Lee, S. Woo and H. N. Lee, "Performance increase by using an EEG sparse representation based classification method" IEEE Int Conf on Consumer Electronics (ICCE), Las Vegas, USA, 201-203, 2013.

[5] Site of Berlin Institute of Technology, Charité- University Medicine Berlin, Available: http://www.bbci.de/competition/iii/desc_IVa.htm.

[6] P. F. Diez, V. Mut, E. Laciar, A. Torres, “Application of the Empirical Mode Decomposition to the Extraction of Features from EEG Signals for Mental Task Classification” 31^st Annu Int Conf of the IEEE/EMBS, Minneapolis, Minnesota, USA, pp 2-6, 2009.

[7] K. K. Ang, Z. Y. Chin, C. Wang, C. Guan, H. Zhang, “Filter bank common spatial pattern algorithm on bci competition iv datasets 2a and 2b” Frontiers in Neuroscience 6 (39), 1-9, 2012.

[8] D. J. McFarland, L. M. McCane, S. V. David, J. R. Wolpaw, "Spatial filter selection for EEG-based communication" Electroencephalographic Clinical Neurophysiology 103, 386–394, 1997.

[9] A. Soong Z. Koles, “Principal component localization of the sources of the background EEG” IEEE Trans on Biomed Eng 42 (1), 59–67, 1995.

[10] B. Blankertz, R. Tomioka, S. Lemm, M. Kawanabe, K. R. Müller, “Optimizing spatial ﬁlters for robust EEG single-trial analysis” IEEE Trans Signal Processing 25 (1), 41–56, 2008.

[11] F. Lotte, C. Guan, “Regularizing Common Spatial Patterns to Improve BCI Designs: Unified Theory and New Algorithms” IEEE Trans biomed Eng v 58 (2), 355-362, 2011.

[12] H. Kang, Y. Nam, S. Choi, “Composite common spatial pattern for subject-to-subject transfer” IEEE Sig Proc Let 16 (8), 683–686, 2009.

[13] F. Lotte, C. Guan, “Spatially regularized common spatial patterns for EEG classification” in Proc ICPR, Istanbul, Turkey, pp 3712–3715, 2010.

[14] E. J. Candes, M. B. Wakin, "An introduction to compressive sampling" IEEE Signal Processing Magazine, pp 21-30, 2008.

[15] E. Candes, J. Romberg, T. Tao, "Stable signal recovery from incomplete and inaccurate surements" Comm Pure Appl Math, pp 1207-1223, 2006.

[16] R. Gribonval, M. Nielsen, "Sparse representations in unions of bases" IEEE Trans Information Theory 49, 3320-3325, 2003.

[17] S. G. Mallat, Z. Zhifeng, "Matching pursuits with time-frequency dictionaries" IEEE Trans Signal Processing 41, 3397-3415, 1993.

[18] Y. C. Pati, R. Rezaiifar, P. S. Krishnaprasad, "Orthogonal matching pursuit: recursive function approximation with applications to wavelet decomposition" in Conf Rec 27^th Asilomar Conf Signals Syst Comput, Pacific Grove, USA, pp 41-44, 1993.

[19] H. Mohimani, M. Babaie-Zadeh, C. H. Jutten, “A fast approach for overcomplete sparse decomposition based on smoothed ℓ0 norm” IEEE Trans Signal Processing 57 (1), 289–301, 2009.